# Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data

arXiv: https://arxiv.org/abs/2112.02825 · HTML: https://mlsanity.com/paper/2112.02825/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 46 references that are in the map.
- First posted on arXiv 6 Dec 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning](https://mlsanity.com/paper/1704.03976/) (2017)
- [Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results](https://mlsanity.com/paper/1703.01780/) (2017)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [Bilinear CNNs for Fine-grained Visual Recognition](https://mlsanity.com/paper/1504.07889/) (2015)
- [CoMatch: Semi-supervised Learning with Contrastive Graph Regularization](https://mlsanity.com/paper/2011.11183/) (2020)
- [Fine-Grained Image Analysis with Deep Learning: A Survey](https://mlsanity.com/paper/2111.06119/) (2021)
- [Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches](https://mlsanity.com/paper/2003.03836/) (2020)
- [SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classification](https://mlsanity.com/paper/2103.16725/) (2021)
- [The Application of Two-level Attention Models in Deep Convolutional Neural Network for Fine-grained Image Classification](https://mlsanity.com/paper/1411.6447/) (2014)
- [A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification](https://mlsanity.com/paper/2104.00679/) (2021)
- [All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training](https://mlsanity.com/paper/2104.05248/) (2021)
- [Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised Learning](https://mlsanity.com/paper/2001.06001/) (2020)
- [RealMix: Towards Realistic Semi-Supervised Deep Learning Algorithms](https://mlsanity.com/paper/1912.08766/) (2019)
- [OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer](https://mlsanity.com/paper/2004.09033/) (2020)
- [The Curious Layperson: Fine-Grained Image Recognition without Expert Labels](https://mlsanity.com/paper/2111.03651/) (2021)
- [ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification](https://mlsanity.com/paper/2006.15366/) (2020)

## Abstract (arXiv)

Despite great strides made on fine-grained visual classification (FGVC), current methods are still heavily reliant on fully-supervised paradigms where ample expert labels are called for. Semi-supervised learning (SSL) techniques, acquiring knowledge from unlabeled data, provide a considerable means forward and have shown great promise for coarse-grained problems. However, exiting SSL paradigms mostly assume in-distribution (i.e., category-aligned) unlabeled data, which hinders their effectiveness when re-proposed on FGVC. In this paper, we put forward a novel design specifically aimed at making out-of-distribution data work for semi-supervised FGVC, i.e., to "clue them in". We work off an important assumption that all fine-grained categories naturally follow a hierarchical structure (e.g., the phylogenetic tree of "Aves" that covers all bird species). It follows that, instead of operating on individual samples, we can instead predict sample relations within this tree structure as the optimization goal of SSL. Beyond this, we further introduced two strategies uniquely brought by these tree structures to achieve inter-sample consistency regularization and reliable pseudo-relation. Our experimental results reveal that (i) the proposed method yields good robustness against out-of-distribution data, and (ii) it can be equipped with prior arts, boosting their performance thus yielding state-of-the-art results. Code is available at https://github.com/PRIS-CV/RelMatch.